
                        
                            import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import seaborn as sns
import matplotlib.pyplot as plt
sns.set_theme()
sns.color_palette("crest", as_cmap=True)
sns.set_palette("crest")
import warnings 
warnings.filterwarnings('ignore')


                        
                            df = pd.read_csv("../data/DSI_kickstarterscrape_dataset.csv")
df.head()


                        
                            # Data cleaning to get rid of repeat and format errors
df["category"][df["category"] == "Film &amp; Video"] = "Film & Video"
df["subcategory"][df["subcategory"] == "Country &amp; Folk"] = "Country & Folk"
df["subcategory"][df["subcategory"] == "Film &amp; Video"] = "Film & Video"
df["subcategory"][df["subcategory"] == "Board &amp; Card Games"] = "Board & Card Games"


df["subcategory"].unique()

array(['Short Film', 'Board & Card Games', 'Animation', 'Documentary',
       'Fashion', 'Music', 'Illustration', 'Film & Video',
       'Open Software', 'Indie Rock', 'Dance', 'Fiction', 'Nonfiction',
       'Theater', 'Games', 'Art Book', 'Country & Folk', 'Comics',
       'Webseries', 'Technology', 'Performance Art', 'Narrative Film',
       'Video Games', 'Product Design', 'Rock', 'Painting', 'Photography',
       'Conceptual Art', 'Jazz', 'Open Hardware', 'Classical Music',
       'Food', 'Art', 'Pop', 'Journalism', 'Poetry', 'Electronic Music',
       'World Music', 'Sculpture', 'Publishing', "Children's Book",
       'Public Art', 'Mixed Media', 'Graphic Design', 'Hip-Hop',
       'Periodical', 'Crafts', 'Design', 'Digital Art'], dtype=object)


                        
                            df["status"].unique()

array(['successful', 'failed', 'live', 'canceled', 'suspended'],
      dtype=object)


                        
                            df["difference between goal and pledge"] = df["goal"] - df["pledged"]


                        
                            df["weekday"] = df["funded date"].str.split(",").str[0]

df["fund date and time"] = df["funded date"].str.split(",").str[1]

df["day"] = df["fund date and time"].str.split(" ").str[1].str.strip().astype("int64")
df["month"] = df["fund date and time"].str.split(" ").str[2].str.strip()
df["year"] = df["fund date and time"].str.split(" ").str[3].str.strip().astype("int64")
df["time"] = df["fund date and time"].str.split(" ").str[4].str.strip()

df["datetime"] = df[['day', 'month', "year"]].astype(str).agg('-'.join, axis=1)
df["datetime"] = df[["datetime", "time"]].agg(" ".join, axis = 1)
df["datetime"] = pd.to_datetime(df["datetime"])

df['hour'] = pd.DatetimeIndex(df['datetime']).hour

months_dict = {"Jan":1, "Feb":2, "Mar":3, "Apr":4, "May":5, "Jun":6, 
                            "Jul":7, "Aug":8, "Sep":9, "Oct":10, "Nov":11, "Dec":12}
df["month numeric"] = df["month"].replace(months_dict)

df = df.drop("fund date and time", axis = 1)


                        
                            df["category and subcategory"] = df["category"]+ " - " + df["subcategory"]
df["category and subcategory"].unique()

array(['Film & Video - Short Film', 'Games - Board & Card Games',
       'Film & Video - Animation', 'Film & Video - Documentary',
       'Fashion - Fashion', 'Music - Music', 'Art - Illustration',
       'Film & Video - Film & Video', 'Technology - Open Software',
       'Music - Indie Rock', 'Dance - Dance', 'Publishing - Fiction',
       'Publishing - Nonfiction', 'Theater - Theater', 'Games - Games',
       'Publishing - Art Book', 'Music - Country & Folk',
       'Comics - Comics', 'Film & Video - Webseries',
       'Technology - Technology', 'Art - Performance Art',
       'Film & Video - Narrative Film', 'Games - Video Games',
       'Design - Product Design', 'Music - Rock', 'Art - Painting',
       'Photography - Photography', 'Art - Conceptual Art',
       'Music - Jazz', 'Technology - Open Hardware',
       'Music - Classical Music', 'Food - Food', 'Art - Art',
       'Music - Pop', 'Publishing - Journalism', 'Publishing - Poetry',
       'Music - Electronic Music', 'Music - World Music',
       'Art - Sculpture', 'Publishing - Publishing',
       "Publishing - Children's Book", 'Art - Public Art',
       'Art - Mixed Media', 'Design - Graphic Design', 'Music - Hip-Hop',
       'Publishing - Periodical', 'Design - Crafts', 'Design - Design',
       'Art - Digital Art'], dtype=object)


                        
                            df = df.sort_values(['category','subcategory'],ascending=[True,True])


                        
                            pd.set_option('display.max_columns', 0)
df.columns = df.columns.str.capitalize()
df.head()


                        
                            sns.set(rc={'axes.facecolor':'white', 'figure.facecolor':'white', 'grid.color':'#d9d9d9', "axes.edgecolor":'#d9d9d9',
                            "font.size": 16, "axes.labelsize" : 18, "xtick.labelsize" : 16, "ytick.labelsize" : 16})

# Create an array with the colors you want to use
colors = ["#7EAF92", "#fc8b8b", "#8DDAD6", "#faeb87", "#f5efcb"]
# Set your custom color palette
sns.set_palette(sns.color_palette(colors))

fig, ax = plt.subplots(figsize=(25,8))
count_status = sns.countplot(data = df, y = "Status")
plt.bar_label(count_status.containers[0], padding = 4)
plt.xlabel("Count")

Text(0.5, 0, 'Count')


                        
                            # Separate successful and failed
df_successful = df[df["Status"] == "successful"]
df_failed = df[df["Status"] == "failed"]


                        
                            fig, ax = plt.subplots(figsize=(15,8))
#sns.displot(data=df, x="Funded percentage", hue = "Status", kde = False)
"""h, bins = np.histogram(df["Funded percentage"], bins = 500000)
y_hist = plt.bar(bins[:-1], h)"""
labels = ["Failed", "Successful"]
percentage_both = [df_successful["Funded percentage"], df_failed["Funded percentage"]]
y_hist= plt.hist(percentage_both, bins =1506600, 
                            histtype = "stepfilled")
plt.xlim(0, 2)
plt.xlabel("Funded Percentage")
plt.ylabel("Count")
plt.legend(labels, loc='upper right')

<matplotlib.legend.Legend at 0x2357bf6a340>


                        
                            # Drop live, canceled and suspended
df = df.drop(df[(df["Status"] == "live") | (df["Status"] == "canceled")| (df["Status"] == "suspended")].index, axis = 0)


                        
                            df = df.drop("Project id", axis = 1)


                        
                            (df_successful["Funded percentage"] >= 1.5).sum()
#np.histogram(df["Funded percentage"], bins = 1506600)

3961


                        
                            #df_successful.corr()
f, ax = plt.subplots(figsize=(14, 14))
sns.heatmap(df_successful.iloc[:,1:].corr(), square = True, annot = True, fmt = '.3f')

<AxesSubplot:>


                        
                            subcategory_count_total = df["Category"].value_counts()
subcategory_count_s = df_successful["Category"].value_counts()
subcategory_count_f = df_failed["Category"].value_counts()
all_counts = pd.concat([subcategory_count_total, subcategory_count_s, subcategory_count_f], axis = 1)
all_counts.columns = ["Total", "Successful", "Failed"]
all_counts.loc['Average']= all_counts.mean()

all_counts["Successful Percentage"] = round(all_counts.Successful/ all_counts.Total*100, 0).astype("int64")
all_counts["Failed Percentage"] = round(all_counts.Failed/ all_counts.Total*100, 0).astype("int64")
all_counts["Total Percentage"] = 100
all_counts_regular = all_counts.iloc[:-1, :].sort_values(by = "Successful Percentage", ascending = False)
all_counts_average = all_counts.iloc[-1:, :]

all_counts = pd.concat([all_counts_regular, all_counts_average], axis = 0)
all_counts


                        
                            fig, ax = plt.subplots(figsize=(25,6))

labels = ["Failed", "Successful"]
#plt.hist(duration_both, bins = round((df["Duration"].max()-df["Duration"].min())/2), density=True)
plt.bar(all_counts.index, all_counts["Total Percentage"], color = "#fc8b8b")
plt.bar(all_counts.index, all_counts["Successful Percentage"], color = "#7EAF92")


plt.ylim(0,100)
ax.yaxis.set_major_locator(plt.MaxNLocator(10))
ax.legend(labels)
plt.xticks(rotation=90)
plt.xlabel("Category")
plt.ylabel("Percentage of success and failure")

Text(0, 0.5, 'Percentage of success and failure')


                        
                            subcategory_count_total = df["Category and subcategory"].value_counts()
subcategory_count_s = df_successful["Category and subcategory"].value_counts()
subcategory_count_f = df_failed["Category and subcategory"].value_counts()
all_counts = pd.concat([subcategory_count_total, subcategory_count_s, subcategory_count_f], axis = 1)
all_counts.columns = ["Total", "Successful", "Failed"]
all_counts.loc['Average']= all_counts.mean()

all_counts["Successful Percentage"] = round(all_counts.Successful/ all_counts.Total*100, 0).astype("int64")
all_counts["Failed Percentage"] = round(all_counts.Failed/ all_counts.Total*100, 0).astype("int64")
all_counts["Total Percentage"] = 100
all_counts_regular = all_counts.iloc[:-1, :].sort_values(by = "Successful Percentage", ascending = False)
all_counts_average = all_counts.iloc[-1:, :]

all_counts = pd.concat([all_counts_regular, all_counts_average], axis = 0)
all_counts

fig, ax = plt.subplots(figsize=(25,6))

labels = ["Failed", "Successful"]
#plt.hist(duration_both, bins = round((df["Duration"].max()-df["Duration"].min())/2), density=True)
plt.bar(all_counts.index, all_counts["Total Percentage"], color = "#fc8b8b")
plt.bar(all_counts.index, all_counts["Successful Percentage"], color = "#7EAF92")


plt.ylim(0,100)
ax.yaxis.set_major_locator(plt.MaxNLocator(10))
ax.legend(labels)
plt.xticks(rotation=90)
plt.xlabel("Subcategory")
plt.ylabel("Percentage of success and failure")

Text(0, 0.5, 'Percentage of success and failure')


                        
                            fig, ax = plt.subplots(figsize=(25,8))

my_order = df_successful.groupby(by="Category")["Funded percentage"].median().sort_values(ascending = True).index

box_subcat = sns.boxplot(data=df_successful, x='Category', y='Funded percentage', hue='Category', palette="Spectral", dodge = False, showfliers = False, order = my_order)
ax.axhline(y = 1, color='red', linewidth=2, alpha=.7, ls='--')
plt.xticks(rotation=90)
plt.ylim(1, 5)
plt.legend(loc='upper left')
my_order

Index(['Dance', 'Film & Video', 'Fashion', 'Theater', 'Food', 'Art', 'Music',
       'Publishing', 'Photography', 'Comics', 'Design', 'Technology', 'Games'],
      dtype='object', name='Category')


                        
                            fig, ax = plt.subplots(figsize=(25,8))

my_order = df_successful.groupby(by="Subcategory")["Funded percentage"].median().sort_values(ascending = True).index

box_subcat = sns.boxplot(data=df_successful, x='Subcategory', y='Funded percentage', hue='Category', palette="Spectral", dodge = False, showfliers = False, order = my_order)
ax.axhline(y = 1, color='red', linewidth=2, alpha=.7, ls='--')
plt.xticks(rotation=90)
plt.ylim(1, 7)
plt.legend(loc='upper left')
my_order

Index(['Narrative Film', 'Performance Art', 'Public Art', 'Short Film',
       'Dance', 'Film & Video', 'Digital Art', 'Jazz', 'Mixed Media', 'Poetry',
       'Documentary', 'Fashion', 'Webseries', 'Theater', 'Food',
       'Children's Book', 'Music', 'Classical Music', 'World Music',
       'Conceptual Art', 'Sculpture', 'Pop', 'Rock', 'Journalism',
       'Publishing', 'Art', 'Indie Rock', 'Country & Folk', 'Hip-Hop',
       'Electronic Music', 'Nonfiction', 'Photography', 'Crafts', 'Periodical',
       'Animation', 'Open Software', 'Painting', 'Fiction', 'Design',
       'Art Book', 'Illustration', 'Video Games', 'Comics', 'Technology',
       'Product Design', 'Graphic Design', 'Board & Card Games', 'Games',
       'Open Hardware'],
      dtype='object', name='Subcategory')


                        
                            fig, ax = plt.subplots(figsize=(25,8))
box_subcat = sns.boxplot(data=df, x='Subcategory', y='Difference between goal and pledge', 
                            hue='Category', palette="Spectral", dodge = False, showfliers = False)
ax.axhline(y = 0, color='grey', linewidth=2, alpha=.7, ls='--')
plt.xticks(rotation=90)
plt.ylim(-25000, 40000) 
plt.legend(loc='upper left')

<matplotlib.legend.Legend at 0x23500ca2460>


                        
                            fig, ax = plt.subplots(figsize=(25,8))
box_subcat = sns.boxplot(data=df, x='Category and subcategory', y='Goal', 
                            hue='Category', palette="Spectral", dodge = False, showfliers = False)
ax.axhline(y = 1, color='grey', linewidth=2, alpha=.7, ls='--')
plt.xticks(rotation=90)
plt.ylim(0, 30000)
plt.legend(loc='upper left')

<matplotlib.legend.Legend at 0x23576435610>


                        
                            fig, ax = plt.subplots(figsize=(25,8))
box_subcat = sns.boxplot(data=df, x='Category and subcategory', y='Pledged', 
                            hue='Category', palette="Spectral", dodge = False, showfliers = False)
ax.axhline(y = 1, color='grey', linewidth=2, alpha=.7, ls='--')
plt.xticks(rotation=90)
plt.ylim(0, 20000)

(0.0, 20000.0)


                        
                            #fig, ax = plt.subplots(figsize=(25,15))
goal_violin = sns.catplot(x="Category and subcategory", y="Goal", hue="Status",
                            kind="violin", split = True, data=df, height = 5, aspect = 5)
plt.ylim(0, 70000)
plt.xticks(rotation=90)

(array([ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16,
        17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33,
        34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48]),
 [Text(0, 0, 'Art - Art'),
  Text(1, 0, 'Art - Conceptual Art'),
  Text(2, 0, 'Art - Digital Art'),
  Text(3, 0, 'Art - Illustration'),
  Text(4, 0, 'Art - Mixed Media'),
  Text(5, 0, 'Art - Painting'),
  Text(6, 0, 'Art - Performance Art'),
  Text(7, 0, 'Art - Public Art'),
  Text(8, 0, 'Art - Sculpture'),
  Text(9, 0, 'Comics - Comics'),
  Text(10, 0, 'Dance - Dance'),
  Text(11, 0, 'Design - Crafts'),
  Text(12, 0, 'Design - Design'),
  Text(13, 0, 'Design - Graphic Design'),
  Text(14, 0, 'Design - Product Design'),
  Text(15, 0, 'Fashion - Fashion'),
  Text(16, 0, 'Film & Video - Animation'),
  Text(17, 0, 'Film & Video - Documentary'),
  Text(18, 0, 'Film & Video - Film & Video'),
  Text(19, 0, 'Film & Video - Narrative Film'),
  Text(20, 0, 'Film & Video - Short Film'),
  Text(21, 0, 'Film & Video - Webseries'),
  Text(22, 0, 'Food - Food'),
  Text(23, 0, 'Games - Board & Card Games'),
  Text(24, 0, 'Games - Games'),
  Text(25, 0, 'Games - Video Games'),
  Text(26, 0, 'Music - Classical Music'),
  Text(27, 0, 'Music - Country & Folk'),
  Text(28, 0, 'Music - Electronic Music'),
  Text(29, 0, 'Music - Hip-Hop'),
  Text(30, 0, 'Music - Indie Rock'),
  Text(31, 0, 'Music - Jazz'),
  Text(32, 0, 'Music - Music'),
  Text(33, 0, 'Music - Pop'),
  Text(34, 0, 'Music - Rock'),
  Text(35, 0, 'Music - World Music'),
  Text(36, 0, 'Photography - Photography'),
  Text(37, 0, 'Publishing - Art Book'),
  Text(38, 0, "Publishing - Children's Book"),
  Text(39, 0, 'Publishing - Fiction'),
  Text(40, 0, 'Publishing - Journalism'),
  Text(41, 0, 'Publishing - Nonfiction'),
  Text(42, 0, 'Publishing - Periodical'),
  Text(43, 0, 'Publishing - Poetry'),
  Text(44, 0, 'Publishing - Publishing'),
  Text(45, 0, 'Technology - Open Hardware'),
  Text(46, 0, 'Technology - Open Software'),
  Text(47, 0, 'Technology - Technology'),
  Text(48, 0, 'Theater - Theater')])


                        
                            df[df["Category"] == "Food"]


                        
                            my_order = df.groupby(by="Category and subcategory")["Goal"].median().sort_values(ascending = False).index

goal_violin = sns.catplot(x="Category and subcategory", y="Goal", hue="Status",
                            kind="box", data=df, height = 5, aspect = 5, showfliers = False, order = my_order)
plt.ylim(0, 70000)
#[ax.axvline(goal_violin, color = 'r', linestyle='--') for x in [1,2,3,4]] # you can put your desired colour instead of red.
plt.xticks(rotation=90)

(array([ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16,
        17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33,
        34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48]),
 [Text(0, 0, 'Design - Product Design'),
  Text(1, 0, 'Technology - Technology'),
  Text(2, 0, 'Technology - Open Hardware'),
  Text(3, 0, 'Film & Video - Documentary'),
  Text(4, 0, 'Film & Video - Narrative Film'),
  Text(5, 0, 'Food - Food'),
  Text(6, 0, 'Design - Design'),
  Text(7, 0, 'Games - Video Games'),
  Text(8, 0, 'Film & Video - Animation'),
  Text(9, 0, 'Technology - Open Software'),
  Text(10, 0, 'Publishing - Nonfiction'),
  Text(11, 0, 'Film & Video - Film & Video'),
  Text(12, 0, 'Film & Video - Webseries'),
  Text(13, 0, 'Games - Board & Card Games'),
  Text(14, 0, 'Fashion - Fashion'),
  Text(15, 0, "Publishing - Children's Book"),
  Text(16, 0, 'Music - Jazz'),
  Text(17, 0, 'Publishing - Publishing'),
  Text(18, 0, 'Publishing - Periodical'),
  Text(19, 0, 'Music - World Music'),
  Text(20, 0, 'Publishing - Art Book'),
  Text(21, 0, 'Music - Pop'),
  Text(22, 0, 'Publishing - Journalism'),
  Text(23, 0, 'Art - Sculpture'),
  Text(24, 0, 'Music - Country & Folk'),
  Text(25, 0, 'Music - Music'),
  Text(26, 0, 'Publishing - Fiction'),
  Text(27, 0, 'Art - Mixed Media'),
  Text(28, 0, 'Photography - Photography'),
  Text(29, 0, 'Film & Video - Short Film'),
  Text(30, 0, 'Art - Public Art'),
  Text(31, 0, 'Music - Classical Music'),
  Text(32, 0, 'Comics - Comics'),
  Text(33, 0, 'Music - Hip-Hop'),
  Text(34, 0, 'Games - Games'),
  Text(35, 0, 'Theater - Theater'),
  Text(36, 0, 'Art - Art'),
  Text(37, 0, 'Design - Crafts'),
  Text(38, 0, 'Dance - Dance'),
  Text(39, 0, 'Music - Indie Rock'),
  Text(40, 0, 'Music - Rock'),
  Text(41, 0, 'Art - Performance Art'),
  Text(42, 0, 'Art - Painting'),
  Text(43, 0, 'Art - Illustration'),
  Text(44, 0, 'Art - Digital Art'),
  Text(45, 0, 'Music - Electronic Music'),
  Text(46, 0, 'Design - Graphic Design'),
  Text(47, 0, 'Publishing - Poetry'),
  Text(48, 0, 'Art - Conceptual Art')])


                        
                            df_median_goal_success = df_successful.groupby('Category and subcategory').agg({'Goal':np.median}).reset_index()
df_median_goal_failed = df_failed.groupby('Category and subcategory').agg({'Goal':np.median}).reset_index()
df_median_goal = pd.concat([df_median_goal_success, df_median_goal_failed], axis = 1)
df_median_goal
#df_median_goal.to_csv("df_median_goal.csv", index=False)


                        
                            """fig, ax = plt.subplots(figsize=(25,15))
scatter_subcat = sns.scatterplot(data=df, x='Duration', y='Funded percentage', hue='Category', palette="Spectral", size = 0.1)
ax.axhline(y = 1, color='red', linewidth=2, alpha=.7, ls='--')
#plt.xticks(rotation=90)
plt.xlim(0, 50)
plt.ylim(0, 5)
plt.legend(loc='upper left')"""

'fig, ax = plt.subplots(figsize=(25,15))\nscatter_subcat = sns.scatterplot(data=df, x=\'Duration\', y=\'Funded percentage\', hue=\'Category\', palette="Spectral", size = 0.1)\nax.axhline(y = 1, color=\'red\', linewidth=2, alpha=.7, ls=\'--\')\n#plt.xticks(rotation=90)\nplt.xlim(0, 50)\nplt.ylim(0, 5)\nplt.legend(loc=\'upper left\')'


                        
                            fig, ax = plt.subplots(figsize=(15,8))
y_hist= plt.hist(df_successful["Duration"].values.flatten(), bins =200, 
                            histtype = "stepfilled", color = "#7EAF92", density = True, stacked = True)
plt.xlim(0, 100)
plt.xlabel("Duration")
plt.ylabel("Density")

Text(0, 0.5, 'Density')


                        
                            fig, ax = plt.subplots(figsize=(15,8))
y_hist= plt.hist(df_failed["Duration"].values.flatten(), bins =200, 
                            histtype = "stepfilled", color = "red", density = True, stacked = True)
plt.xlim(0, 100)
plt.xlabel("Duration")
plt.ylabel("Density")

Text(0, 0.5, 'Density')


                        
                            goal_violin = sns.catplot(x="Category and subcategory", y="Duration", hue="Status",
                            kind="box", data=df, height = 10, aspect = 5, showfliers = False)
plt.ylim(0, 100)
plt.xticks(rotation=90)
#

(array([ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16,
        17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33,
        34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48]),
 [Text(0, 0, 'Art - Art'),
  Text(1, 0, 'Art - Conceptual Art'),
  Text(2, 0, 'Art - Digital Art'),
  Text(3, 0, 'Art - Illustration'),
  Text(4, 0, 'Art - Mixed Media'),
  Text(5, 0, 'Art - Painting'),
  Text(6, 0, 'Art - Performance Art'),
  Text(7, 0, 'Art - Public Art'),
  Text(8, 0, 'Art - Sculpture'),
  Text(9, 0, 'Comics - Comics'),
  Text(10, 0, 'Dance - Dance'),
  Text(11, 0, 'Design - Crafts'),
  Text(12, 0, 'Design - Design'),
  Text(13, 0, 'Design - Graphic Design'),
  Text(14, 0, 'Design - Product Design'),
  Text(15, 0, 'Fashion - Fashion'),
  Text(16, 0, 'Film & Video - Animation'),
  Text(17, 0, 'Film & Video - Documentary'),
  Text(18, 0, 'Film & Video - Film & Video'),
  Text(19, 0, 'Film & Video - Narrative Film'),
  Text(20, 0, 'Film & Video - Short Film'),
  Text(21, 0, 'Film & Video - Webseries'),
  Text(22, 0, 'Food - Food'),
  Text(23, 0, 'Games - Board & Card Games'),
  Text(24, 0, 'Games - Games'),
  Text(25, 0, 'Games - Video Games'),
  Text(26, 0, 'Music - Classical Music'),
  Text(27, 0, 'Music - Country & Folk'),
  Text(28, 0, 'Music - Electronic Music'),
  Text(29, 0, 'Music - Hip-Hop'),
  Text(30, 0, 'Music - Indie Rock'),
  Text(31, 0, 'Music - Jazz'),
  Text(32, 0, 'Music - Music'),
  Text(33, 0, 'Music - Pop'),
  Text(34, 0, 'Music - Rock'),
  Text(35, 0, 'Music - World Music'),
  Text(36, 0, 'Photography - Photography'),
  Text(37, 0, 'Publishing - Art Book'),
  Text(38, 0, "Publishing - Children's Book"),
  Text(39, 0, 'Publishing - Fiction'),
  Text(40, 0, 'Publishing - Journalism'),
  Text(41, 0, 'Publishing - Nonfiction'),
  Text(42, 0, 'Publishing - Periodical'),
  Text(43, 0, 'Publishing - Poetry'),
  Text(44, 0, 'Publishing - Publishing'),
  Text(45, 0, 'Technology - Open Hardware'),
  Text(46, 0, 'Technology - Open Software'),
  Text(47, 0, 'Technology - Technology'),
  Text(48, 0, 'Theater - Theater')])


                        
                            fig, ax = plt.subplots(figsize=(15,8))

labels = ["Successful", "Failed"]
duration_both = [df_successful["Duration"], df_failed["Duration"]]
#plt.hist(duration_both, bins = round((df["Duration"].max()-df["Duration"].min())/2), density=True)
plt.hist(duration_both, bins =45, density=False)

plt.xlim(0,100)
ax.xaxis.set_major_locator(plt.MaxNLocator(20))
plt.xlabel("Duration")
plt.ylabel("Count")
ax.legend(labels)

<matplotlib.legend.Legend at 0x23503592550>


                        
                            fig, ax = plt.subplots(figsize=(15,8))

labels = ["Successful", "Failed"]
duration_both = [df_successful["Duration"], df_failed["Duration"]]
duration_hist_2 = plt.hist(duration_both, 
                            bins = [df["Duration"].min(),45, 58, df["Duration"].max()], 
                            density=False)

ax.invert_yaxis()
ax.xaxis.tick_top()

plt.xlim(0,100)
ax.xaxis.set_major_locator(plt.MaxNLocator(10))
ax.legend(labels, loc = "lower right")
#plt.xlabel("Duration")
plt.ylabel("Count")

Text(0, 0.5, 'Count')


                        
                            """from matplotlib.animation import FuncAnimation
#plt.style.use('seaborn-pastel')


fig, ax = plt.subplots(figsize=(15,8))
plt.xlim(0,100)
ax.xaxis.set_major_locator(plt.MaxNLocator(10))

line, = ax.plot([], [], lw=3)

def init():
    line.set_data([], [])
    return line,
def animate(i):
    x = np.linspace(0, 4, 1000)
    y = np.sin(2 * np.pi * (x - 0.01 * i))
    line.set_data(x, y)
    return line,

anim = FuncAnimation(fig, animate, init_func=init,
                               frames=200, interval=20, blit=True)


anim.save('sine_wave.gif', writer='imagemagick')"""

"from matplotlib.animation import FuncAnimation\n#plt.style.use('seaborn-pastel')\n\n\nfig, ax = plt.subplots(figsize=(15,8))\nplt.xlim(0,100)\nax.xaxis.set_major_locator(plt.MaxNLocator(10))\n\nline, = ax.plot([], [], lw=3)\n\ndef init():\n    line.set_data([], [])\n    return line,\ndef animate(i):\n    x = np.linspace(0, 4, 1000)\n    y = np.sin(2 * np.pi * (x - 0.01 * i))\n    line.set_data(x, y)\n    return line,\n\nanim = FuncAnimation(fig, animate, init_func=init,\n                               frames=200, interval=20, blit=True)\n\n\nanim.save('sine_wave.gif', writer='imagemagick')"


                        
                            fig, ax = plt.subplots(figsize=(15,8))
goal_duration = sns.scatterplot(y="Goal", x="Duration", hue="Status", data=df)

plt.ylim(0, 400000)
plt.xlim(0, 100)

(0.0, 100.0)


                        
                            fig, ax = plt.subplots(figsize=(25,15))
sns.scatterplot(data = df, x = "Datetime", y = "Funded percentage", hue = "Status" )
plt.ylim(0, 5)
plt.xticks(rotation=90)

(array([14365., 14488., 14610., 14730., 14853., 14975., 15095., 15218.,
        15340., 15461.]),
 [Text(0, 0, ''),
  Text(0, 0, ''),
  Text(0, 0, ''),
  Text(0, 0, ''),
  Text(0, 0, ''),
  Text(0, 0, ''),
  Text(0, 0, ''),
  Text(0, 0, ''),
  Text(0, 0, ''),
  Text(0, 0, '')])


                        
                            fig, ax = plt.subplots(figsize=(8,8))

# Draw cumulative line
plt.hist(df["Datetime"], bins =1000, 
                            histtype = "step", cumulative= True, color = '#027173')
# Plot total bar
bins =[df["Datetime"].min(), pd.to_datetime("1-1-2010"), pd.to_datetime("1-1-2011"), pd.to_datetime("1-1-2012"), df["Datetime"].max()]

# Plot success bar
plt.hist(df["Datetime"], bins =bins, histtype = "bar", color = "#fc8b8b")
# Plot success bar
plt.hist(df_successful["Datetime"], bins =bins, histtype = "bar", color = "#7EAF92")
plt.xticks(rotation = 90)

labels = ["Total Projects", "Successful", "Failed"]
plt.legend(labels, loc = "upper left")
plt.xlabel("Time")
plt.ylabel("Number of projects")
print()


                        
                            fig, ax = plt.subplots(figsize=(4,8))
box_subcat = sns.boxplot(data=df_successful, x='Year', y='Funded percentage', 
                            palette="Spectral", dodge = False, showfliers = False)
ax.axhline(y = 1, color='grey', linewidth=2, alpha=.7, ls='--')
plt.ylabel("Funded percentage for successful projects")
plt.ylim(1, 2.1)

(1.0, 2.1)


                        
                            fig, ax = plt.subplots(figsize=(8,8))

# Plot success bar
plt.hist(df["Month numeric"], bins =12, histtype = "bar", color = "#fc8b8b")
# Plot success bar
plt.hist(df_successful["Month numeric"], bins =12, histtype = "bar", color = "#7EAF92")
plt.xticks(rotation = 90)

labels = ["Failed", "Successful"]
plt.legend(labels, loc = "upper left")
plt.xlabel("Month")
plt.ylabel("Number of projects")
ax.set_xticklabels(months, rotation=90) #set the labels and rotate them 90 deg.
plt.xticks(np.arange(1, 13, 1))
print()


                        
                            month_count_total = df["Month"].value_counts()
month_count_successful = df_successful["Month"].value_counts()
month_count_failed = df_failed["Month"].value_counts()
month_all_counts = pd.concat([month_count_total, month_count_successful, month_count_failed], axis = 1)
column = ["Total", "Successful", "Failed"]
month_all_counts["Successful Percentage"] = round(month_count_successful/month_count_total*100).astype("int64")
month_all_counts["Failed Percentage"] = round(month_count_failed/month_count_total*100).astype("int64")
month_all_counts["Total Percentage"] = 100


months = ["Jan", "Feb", "Mar", "Apr", "May", "Jun", 
                            "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"]
month_all_counts = month_all_counts.reindex(months)
month_all_counts


                        
                            fig, ax = plt.subplots(figsize=(8,8))

labels = ["Failed", "Successful"]
#plt.hist(duration_both, bins = round((df["Duration"].max()-df["Duration"].min())/2), density=True)
plt.bar(month_all_counts.index, month_all_counts["Total Percentage"], color = "#fc8b8b")
plt.bar(month_all_counts.index, month_all_counts["Successful Percentage"], color = "#7EAF92")


plt.ylim(0,100)
ax.yaxis.set_major_locator(plt.MaxNLocator(10))
ax.legend(labels)
plt.xticks(rotation=90)
plt.xticks(rotation=90)
plt.xlabel("Months")
plt.ylabel("Percentage of success and failure")

Text(0, 0.5, 'Percentage of success and failure')


                        
                            fig, ax = plt.subplots(figsize=(4,8))
box_subcat = sns.boxplot(data=df_successful, x='Month', y='Funded percentage', 
                            palette="Spectral", dodge = False, showfliers = False, order = months)
ax.axhline(y = 1, color='grey', linewidth=2, alpha=.7, ls='--')
plt.ylabel("Funded percentage for successful projects")
plt.ylim(1, 1.9)
plt.xticks(rotation = 90)
print()

	project id	name	url	category	subcategory	location	status	goal	pledged	funded percentage	backers	funded date	levels	reward levels	updates	comments	duration
0	39409	WHILE THE TREES SLEEP	http://www.kickstarter.com/projects/emiliesaba...	Film & Video	Short Film	Columbia, MO	successful	10500.0	11545.0	1.099524	66	Fri, 19 Aug 2011 19:28:17 -0000	7	$25,$50,$100,$250,$500,$1,000,$2,500	10	2	30.00
1	126581	Educational Online Trading Card Game	http://www.kickstarter.com/projects/972789543/...	Games	Board & Card Games	Maplewood, NJ	failed	4000.0	20.0	0.005000	2	Mon, 02 Aug 2010 03:59:00 -0000	5	$1,$5,$10,$25,$50	6	0	47.18
2	138119	STRUM	http://www.kickstarter.com/projects/185476022/...	Film & Video	Animation	Los Angeles, CA	live	20000.0	56.0	0.002800	3	Fri, 08 Jun 2012 00:00:31 -0000	10	$1,$10,$25,$40,$50,$100,$250,$1,000,$1,337,$9,001	1	0	28.00
3	237090	GETTING OVER - One son's search to finally kno...	http://www.kickstarter.com/projects/charnick/g...	Film & Video	Documentary	Los Angeles, CA	successful	6000.0	6535.0	1.089167	100	Sun, 08 Apr 2012 02:14:00 -0000	13	$1,$10,$25,$30,$50,$75,$85,$100,$110,$250,$500...	4	0	32.22
4	246101	The Launch of FlyeGrlRoyalty "The New Nam...	http://www.kickstarter.com/projects/flyegrlroy...	Fashion	Fashion	Novi, MI	failed	3500.0	0.0	0.000000	0	Wed, 01 Jun 2011 15:25:39 -0000	6	$10,$25,$50,$100,$150,$250	2	0	30.00

	Project id	Name	Url	Category	Subcategory	Location	Status	Goal	Pledged	Funded percentage	Backers	Funded date	Levels	Reward levels	Updates	Comments	Duration	Difference between goal and pledge	Weekday	Day	Month	Year	Time	Datetime	Hour	Month numeric	Category and subcategory
96	4684967	Brooklyn Pop-Up Show: VULNERABLE	http://www.kickstarter.com/projects/229collect...	Art	Art	Brooklyn, NY	successful	500.0	563.0	1.12600	25	Fri, 06 Apr 2012 16:31:08 -0000	4	$5,$25,$50,$150	2	0	27.96	-63.0	Fri	6	Apr	2012	16:31:08	2012-04-06 16:31:08	16	4	Art - Art
100	4732285	Insiders/Out: Exploring Outsider Art in America	http://www.kickstarter.com/projects/insidersou...	Art	Art	NaN	successful	2000.0	2000.0	0.99983	30	Thu, 08 Jul 2010 21:39:00 -0000	13	$1,$5,$10,$15,$20,$25,$35,$50,$75,$100,$150,$2...	4	1	42.97	0.0	Thu	8	Jul	2010	21:39:00	2010-07-08 21:39:00	21	7	Art - Art
190	9729076	parallels: defining home	http://www.kickstarter.com/projects/981542607/...	Art	Art	Grand Rapids, MI	successful	2500.0	2500.0	1.00000	33	Sat, 05 Feb 2011 04:44:57 -0000	7	$10,$25,$50,$75,$150,$300,$500	1	0	12.00	0.0	Sat	5	Feb	2011	04:44:57	2011-02-05 04:44:57	4	2	Art - Art
193	9993639	Greenspirit Arts RE-LAUNCH of Limited-Edition ...	http://www.kickstarter.com/projects/551175469/...	Art	Art	Westport, NY	successful	8000.0	8940.0	1.11750	74	Mon, 21 Mar 2011 03:59:00 -0000	11	$1,$5,$10,$20,$40,$60,$100,$250,$475,$500,$600	25	5	39.37	-940.0	Mon	21	Mar	2011	03:59:00	2011-03-21 03:59:00	3	3	Art - Art
231	11201727	Inspiring and Lifting Lives... Through Art!	http://www.kickstarter.com/projects/aa2d/most-...	Art	Art	Austin, TX	failed	750.0	18.0	0.02400	3	Wed, 12 Oct 2011 05:16:35 -0000	11	$1,$5,$12,$20,$50,$100,$325,$750,$1,000,$2,000...	1	0	21.00	732.0	Wed	12	Oct	2011	05:16:35	2011-10-12 05:16:35	5	10	Art - Art

	Name	Url	Category	Subcategory	Location	Status	Goal	Pledged	Funded percentage	Backers	Funded date	Levels	Reward levels	Updates	Comments	Duration	Difference between goal and pledge	Weekday	Day	Month	Year	Time	Datetime	Hour	Month numeric	Category and subcategory
76	HAPPY AS A CLAM	http://www.kickstarter.com/projects/1114111720...	Food	Food	St Augustine, FL	failed	80000.0	0.0	0.000000	0	Tue, 07 Feb 2012 00:09:05 -0000	7	$25,$50,$100,$500,$1,000,$5,000,$7,500	0	0	60.00	80000.0	Tue	7	Feb	2012	00:09:05	2012-02-07 00:09:05	0	2	Food - Food
83	TOMATOCLAM et al	http://www.kickstarter.com/projects/1795134881...	Food	Food	Virginia Beach, VA	failed	100000.0	0.0	0.000000	0	Tue, 07 Feb 2012 21:42:28 -0000	2	$50,$50	0	0	45.00	100000.0	Tue	7	Feb	2012	21:42:28	2012-02-07 21:42:28	21	2	Food - Food
113	Great Beer Goes Down Easy	http://www.kickstarter.com/projects/1284366959...	Food	Food	Houston, TX	failed	55000.0	2565.0	0.046636	15	Fri, 09 Mar 2012 00:00:00 -0000	18	$1,$5,$10,$25,$35,$50,$100,$150,$250,$300,$500...	7	0	34.43	52435.0	Fri	9	Mar	2012	00:00:00	2012-03-09 00:00:00	0	3	Food - Food
144	Robotic First Fruits Farm-Sustainable Food, En...	http://www.kickstarter.com/projects/1651556528...	Food	Food	Germantown, MD	failed	25000.0	362.0	0.014480	18	Fri, 24 Feb 2012 17:09:45 -0000	26	$5,$10,$15,$25,$30,$30,$33,$33,$35,$45,$55,$65...	2	0	45.00	24638.0	Fri	24	Feb	2012	17:09:45	2012-02-24 17:09:45	17	2	Food - Food
152	NADIA'S KITCHEN. Moroccan food stand in Brookl...	http://www.kickstarter.com/projects/1877029566...	Food	Food	Brooklyn, NY	failed	3000.0	1005.0	0.335000	20	Sun, 18 Mar 2012 05:39:33 -0000	8	$1,$5,$10,$20,$50,$100,$500,$1,000	1	0	11.96	1995.0	Sun	18	Mar	2012	05:39:33	2012-03-18 05:39:33	5	3	Food - Food
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
45841	Macaron Porn: Parisian Recipes	http://www.kickstarter.com/projects/jennijaime...	Food	Food	Gainesville, FL	failed	4500.0	110.0	0.024444	4	Fri, 09 Mar 2012 03:18:36 -0000	8	$10,$25,$50,$75,$125,$200,$500,$1,000	2	0	45.00	4390.0	Fri	9	Mar	2012	03:18:36	2012-03-09 03:18:36	3	3	Food - Food
45842	Macaron Porn: Parisian Recipes	http://www.kickstarter.com/projects/jennijaime...	Food	Food	Gainesville, FL	failed	4500.0	110.0	0.024444	4	Fri, 09 Mar 2012 03:18:36 -0000	8	$10,$25,$50,$75,$125,$200,$500,$1,000	2	0	45.00	4390.0	Fri	9	Mar	2012	03:18:36	2012-03-09 03:18:36	3	3	Food - Food
45843	Stickmen Brewery & Skewery	http://www.kickstarter.com/projects/1926119894...	Food	Food	Lake Oswego, OR	failed	30000.0	3836.0	0.127867	42	Thu, 01 Mar 2012 23:00:00 -0000	11	$5,$15,$25,$50,$100,$250,$500,$1,000,$2,500,$5...	3	2	42.24	26164.0	Thu	1	Mar	2012	23:00:00	2012-03-01 23:00:00	23	3	Food - Food
45844	Stickmen Brewery & Skewery	http://www.kickstarter.com/projects/1926119894...	Food	Food	Lake Oswego, OR	failed	30000.0	3836.0	0.127867	42	Thu, 01 Mar 2012 23:00:00 -0000	11	$5,$15,$25,$50,$100,$250,$500,$1,000,$2,500,$5...	3	2	42.24	26164.0	Thu	1	Mar	2012	23:00:00	2012-03-01 23:00:00	23	3	Food - Food
45936	The Best Little Sweet Shop in Vegas: Naked Cit...	http://www.kickstarter.com/projects/781435581/...	Food	Food	Las Vegas, NV	failed	10000.0	252.0	0.025200	6	Sat, 24 Mar 2012 01:46:13 -0000	19	$1,$10,$25,$50,$75,$100,$100,$125,$150,$150,$1...	0	0	59.96	9748.0	Sat	24	Mar	2012	01:46:13	2012-03-24 01:46:13	1	3	Food - Food

Kickstarter Dataset Analysis¶

Import Libraries¶

Load Data¶

Data Cleaning¶

Combine funding status¶

Make new features¶

Difference between goal and pledged¶

Date¶

Analysis¶

Response Variable¶

Predictor¶

Cateogory and Subcategory¶

Goal and Pledged¶

Duration¶

Time¶

	Total	Successful	Failed	Successful Percentage	Failed Percentage	Total Percentage
Dance	707.000000	527.000000	180.000000	75	25	100
Theater	2322.000000	1642.000000	680.000000	71	29	100
Music	10053.000000	6792.000000	3261.000000	68	32	100
Art	3691.000000	2106.000000	1585.000000	57	43	100
Comics	968.000000	520.000000	448.000000	54	46	100
Film & Video	12595.000000	6423.000000	6172.000000	51	49	100
Food	1298.000000	655.000000	643.000000	50	50	100
Design	1566.000000	729.000000	837.000000	47	53	100
Photography	1387.000000	645.000000	742.000000	47	53	100
Games	1467.000000	635.000000	832.000000	43	57	100
Publishing	4155.000000	1671.000000	2484.000000	40	60	100
Technology	737.000000	289.000000	448.000000	39	61	100
Fashion	1019.000000	335.000000	684.000000	33	67	100
Average	3228.076923	1766.846154	1461.230769	55	45	100

	Category and subcategory	Goal	Category and subcategory	Goal
0	Art - Art	2500.00	Art - Art	3316.5
1	Art - Conceptual Art	1500.00	Art - Conceptual Art	3500.0
2	Art - Digital Art	1000.00	Art - Digital Art	5000.0
3	Art - Illustration	2500.00	Art - Illustration	3000.0
4	Art - Mixed Media	2400.00	Art - Mixed Media	5000.0
5	Art - Painting	2000.00	Art - Painting	3500.0
6	Art - Performance Art	2000.00	Art - Performance Art	3000.0
7	Art - Public Art	2500.00	Art - Public Art	5000.0
8	Art - Sculpture	2500.00	Art - Sculpture	5000.0
9	Comics - Comics	2500.00	Comics - Comics	5000.0
10	Dance - Dance	2500.00	Dance - Dance	3000.0
11	Design - Crafts	1200.00	Design - Crafts	3500.0
12	Design - Design	5000.00	Design - Design	9950.0
13	Design - Graphic Design	1500.00	Design - Graphic Design	3250.0
14	Design - Product Design	8000.00	Design - Product Design	12000.0
15	Fashion - Fashion	3000.00	Fashion - Fashion	5000.0
16	Film & Video - Animation	3200.00	Film & Video - Animation	10000.0
17	Film & Video - Documentary	6000.00	Film & Video - Documentary	10000.0
18	Film & Video - Film & Video	3500.00	Film & Video - Film & Video	7900.0
19	Film & Video - Narrative Film	5000.00	Film & Video - Narrative Film	11000.0
20	Film & Video - Short Film	2500.00	Film & Video - Short Film	4500.0
21	Film & Video - Webseries	3000.00	Film & Video - Webseries	5000.0
22	Food - Food	5000.00	Food - Food	10000.0
23	Games - Board & Card Games	5000.00	Games - Board & Card Games	8000.0
24	Games - Games	2500.00	Games - Games	5500.0
25	Games - Video Games	5000.00	Games - Video Games	8000.0
26	Music - Classical Music	2750.00	Music - Classical Music	5000.0
27	Music - Country & Folk	3000.00	Music - Country & Folk	5000.0
28	Music - Electronic Music	2000.00	Music - Electronic Music	2500.0
29	Music - Hip-Hop	2100.00	Music - Hip-Hop	4000.0
30	Music - Indie Rock	2500.00	Music - Indie Rock	3500.0
31	Music - Jazz	3150.00	Music - Jazz	6250.0
32	Music - Music	3000.00	Music - Music	4000.0
33	Music - Pop	3000.00	Music - Pop	5000.0
34	Music - Rock	2400.00	Music - Rock	2650.0
35	Music - World Music	3467.17	Music - World Music	5000.0
36	Photography - Photography	2500.00	Photography - Photography	4000.0
37	Publishing - Art Book	2200.00	Publishing - Art Book	5000.0
38	Publishing - Children's Book	3287.50	Publishing - Children's Book	5000.0
39	Publishing - Fiction	1500.00	Publishing - Fiction	3500.0
40	Publishing - Journalism	2500.00	Publishing - Journalism	5000.0
41	Publishing - Nonfiction	3000.00	Publishing - Nonfiction	5500.0
42	Publishing - Periodical	2500.00	Publishing - Periodical	6000.0
43	Publishing - Poetry	1500.00	Publishing - Poetry	3000.0
44	Publishing - Publishing	2500.00	Publishing - Publishing	5000.0
45	Technology - Open Hardware	6000.00	Technology - Open Hardware	10000.0
46	Technology - Open Software	4048.00	Technology - Open Software	8000.0
47	Technology - Technology	6000.00	Technology - Technology	13000.0
48	Theater - Theater	2500.00	Theater - Theater	4500.0

	Month	Month	Month	Successful Percentage	Failed Percentage	Total Percentage
Jan	3105	1659	1446	53	47	100
Feb	3233	1764	1469	55	45	100
Mar	4559	2592	1967	57	43	100
Apr	5126	2929	2197	57	43	100
May	5708	3044	2664	53	47	100
Jun	2848	1536	1312	54	46	100
Jul	2847	1511	1336	53	47	100
Aug	3044	1666	1378	55	45	100
Sep	2755	1496	1259	54	46	100
Oct	2801	1530	1271	55	45	100
Nov	2640	1517	1123	57	43	100
Dec	3299	1725	1574	52	48	100